feat(telegram): stop generation from the client, questions survive a restart, images reach the model inline, albums become one turn

src/beaver_gateway/conversations/turns.py

@@ -3,10 +3,12 @@
 from __future__ import annotations
 
 import asyncio
+import base64
 import contextlib
 import inspect
 import logging
 from datetime import UTC, datetime
+from pathlib import Path
 from typing import TYPE_CHECKING, Any, cast
 from uuid import uuid4
 
@@ -34,7 +36,7 @@ if TYPE_CHECKING:
 
     from beaver_gateway.events.stream import MessageStreamEvent
 
-__all__ = ["Turns"]
+__all__ = ["Turns", "content_of", "image_block"]
 
 _log = logging.getLogger(__name__)
 
@@ -125,13 +127,14 @@ class Turns(Seeds):
         tools: bool = True,
         turn_id: str | None = None,
         item_origin: str | None = None,
+        attachments: Sequence[dict[str, Any]] | None = None,
     ) -> tuple[str, TurnCapture]:
         capture = TurnCapture()
         acc = StreamAccumulator()
         agent = self._claude_agent(conv.agent_name)
         async for event in self.turn(
             conv,
-            messages=[{"role": "user", "content": text}],
+            messages=[{"role": "user", "content": content_of(text, attachments)}],
             origin=origin,
             capture=capture,
             tools=tools,
@@ -224,7 +227,12 @@ class Turns(Seeds):
             prompt = f"{seed}\n\n{prompt}"
         try:
             text, capture = await self.run_text_turn(
-                conv, prompt, origin=origin, turn_id=turn_id, item_origin=head.origin
+                conv,
+                prompt,
+                origin=origin,
+                turn_id=turn_id,
+                item_origin=head.origin,
+                attachments=head.attachments if origin == "user" else None,
             )
         except Exception:  # noqa: BLE001
             _log.exception("turn %s on %s failed", turn_id, conv.external_id)
@@ -402,6 +410,33 @@ class Turns(Seeds):
         await self._update(conv, apply)
 
 
+IMAGE_MAX_BYTES = 5 * 1024 * 1024
+
+
+def content_of(
+    text: str, attachments: Sequence[dict[str, Any]] | None
+) -> str | list[dict[str, Any]]:
+    """Plain text, or text plus the images that ride with it."""
+    blocks = [b for a in attachments or () if (b := image_block(a)) is not None]
+    if not blocks:
+        return text
+    return [{"type": "text", "text": text}, *blocks]
+
+
+def image_block(attachment: dict[str, Any]) -> dict[str, Any] | None:
+    media_type = str(attachment.get("media_type") or "")
+    path = Path(str(attachment.get("path") or ""))
+    if not media_type.startswith("image/") or not path.is_file():
+        return None
+    if path.stat().st_size > IMAGE_MAX_BYTES:
+        return None
+    data = base64.b64encode(path.read_bytes()).decode("ascii")
+    return {
+        "type": "image",
+        "source": {"type": "base64", "media_type": media_type, "data": data},
+    }
+
+
 def _prompt_preview(messages: Sequence[Any], limit: int = 400) -> str | None:
     if not messages:
         return None